Intel Arc A380 vs Intel UHD Graphics 750 Comparison

Intel
GPU

Intel Arc A380

CORE STATE DG2-128
VRAM 6 GB
CLOCK SPEED 2050 MHz
TDP 75 W
BUS WIDTH 96 bit
ARCHITECTURE Xe-HPG
nm
PROCESS 6 nm
LAUNCH DATE 2022
VS
Intel
GPU

UHD Graphics 750

CORE STATE Rocket Lake
VRAM System Shared
CLOCK SPEED 1300 MHz
TDP 15 W
BUS WIDTH System Shared
ARCHITECTURE Generation 12.1
nm
PROCESS 14 nm+++
LAUNCH DATE 2021

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
808
N/A
geekbench_opencl
38,224
6,743
geekbench_vulkan
36,736
8,138
passmark_directx_10
37
N/A
passmark_directx_11
38
N/A
passmark_directx_12
35
N/A
passmark_directx_9
73
N/A
passmark_g2d
610
N/A
passmark_g3d
6,252
N/A
passmark_gpu_compute
2,762
N/A

Analysis: Intel Arc A380 vs Intel UHD Graphics 750

The Verdict

The Intel Arc A380 is the clear performance winner in every recorded head-to-head measurement. In Geekbench OpenCL, it scores 38,224 versus 6,743 for the Intel UHD Graphics 750, a 466.9% advantage. In Geekbench Vulkan, the Arc A380 scores 36,736 versus 8,138, a 351.4% lead. If you need actual graphics work, gaming, or compute acceleration, the Arc A380 is the only choice from these two.

The Intel UHD Graphics 750 is an integrated GPU (IGP) with a 15 W TDP. It exists to provide basic display output and light acceleration for office tasks, video playback, and very old or low-demand games. The recorded data shows its average benchmark score is 7,441, placing it at the 40th percentile of all GPUs. Its nearest rivals include the NVIDIA GeForce GTX 1650 (average score 7,472, delta -0.4%) and the Intel Arc A310 (average score 7,550, delta -1.4%). For an IGP, it is not embarrassing, but it is firmly in entry-level territory.

The Arc A380, by contrast, sits at the 44th percentile of all GPUs with an average benchmark score of 8,558. Its nearest rivals include the AMD Radeon 880M (avg 8,436, delta 1.4%) and the NVIDIA GeForce MX330 (avg 8,458, delta 1.2%). These are all discrete or high-end integrated solutions that are close to the A380 in aggregate score, though the A380's win in the two Geekbench tests is decisive.

Pick the Arc A380 if you need a real discrete GPU with its own 6 GB of GDDR6 memory, high compute throughput, and modern API support. Pick the UHD Graphics 750 only if you are building a low-power system with no expansion slot for a GPU and you accept its integrated limitations.

Architecture Differences

The two Intel GPUs come from entirely different design lineages. The Arc A380 uses the DG2-128 chip based on the Xe-HPG architecture, belonging to the Alchemist generation (Arc 3). It is fabricated on a 6 nm TSMC process and contains 7,200 million transistors on a 157 mm² die, giving a transistor density of 45.9 million per square millimeter. The UHD Graphics 750 uses the Rocket Lake chip based on Generation 12.1, in the HD Graphics (Rocket Lake) family. It is built on Intel's 14 nm+++ process. The UHD 750's transistor count and die size are not recorded in the database.

The Arc A380 has 1,204 shading units, 64 texture mapping units, and 32 ROPs. It also includes 8 ray tracing cores, a notable addition for an entry-level card. The UHD Graphics 750 has 256 shading units, 16 TMUs, and 8 ROPs, with no ray tracing cores listed. The Arc A380 supports DirectX 12 Ultimate (12_2), whereas the UHD 750 supports DirectX 12 (12_1). Both support OpenGL 4.6 and Vulkan 1.4.

Memory architecture is a major separation. The Arc A380 has 6 GB of GDDR6 on a 96-bit bus, delivering 186.0 GB/s of bandwidth. The UHD Graphics 750 uses system shared memory, with its bus width, memory type, and bandwidth all listed as system dependent. This means the UHD Graphics 750's memory performance depends entirely on the host system's RAM configuration.

Clock speeds differ strongly. The Arc A380 runs at a 2000 MHz base and 2050 MHz boost. The UHD Graphics 750 runs at a 300 MHz base and 1300 MHz boost. That boost clock is far below the Arc's base clock. Pixel and texture rates follow the same pattern: the Arc A380 delivers 65.60 GPixel/s and 131.2 GTexel/s, while the UHD Graphics 750 manages 10.40 GPixel/s and 20.80 GTexel/s. Compute output is similarly lopsided: the Arc A380 produces 4.198 TFLOPS FP32 and 8.397 TFLOPS FP16, while the UHD 750 produces 665.6 GFLOPS FP32 and 1,331.2 GFLOPS FP16.

FAQ

Q: Which GPU is faster in the recorded benchmarks?

A: The Arc A380 wins both head-to-head tests. In Geekbench OpenCL it scores 38,224 versus 6,743 (466.9% higher), and in Geekbench Vulkan it scores 36,736 versus 8,138 (351.4% higher).

Q: Does the UHD Graphics 750 have any ray tracing capability?

A: No. The UHD Graphics 750 has no ray tracing cores listed in the database. The Arc A380 includes 8 dedicated ray tracing cores.

Q: What memory configurations do they use?

A: The Arc A380 has 6 GB of GDDR6 memory on a 96-bit bus, with 186.0 GB/s bandwidth. The UHD Graphics 750 uses system shared memory, with bandwidth listed as system dependent.

Q: Which GPU has better API support for modern games?

A: The Arc A380 supports DirectX 12 Ultimate (12_2), the newer feature level. The UHD Graphics 750 supports DirectX 12 (12_1). Both support OpenGL 4.6 and Vulkan 1.4.

Q: Which GPU is more efficient in terms of power draw?

A: The UHD Graphics 750 has a 15 W TDP and is an integrated solution. The Arc A380 has a 75 W TDP and requires a dual-slot cooler with a 1x 8-pin power connector and a 250 W suggested PSU.

Q: How does the Arc A380 compare to its nearest rivals?

A: Its average benchmark score of 8,558 places it 0.4% behind the AMD FirePro W5170M (8,595), 1.1% ahead of the AMD Radeon HD 8870M (8,462), 1.2% ahead of the NVIDIA GeForce MX330 (8,458), and 1.4% ahead of the AMD Radeon 880M (8,436).

Specification Differences

| Field | Intel Arc A380 | Intel UHD Graphics 750 |

|---|---|---|

| Chip | DG2-128 | Rocket Lake |

| Architecture | Xe-HPG | Generation 12.1 |

| Generation | Alchemist (Arc 3) | HD Graphics (Rocket Lake) |

| Process node | 6 nm | 14 nm+++ |

| Foundry | TSMC | Intel |

| Transistors | 7,200 million | N/A |

| Die size | 157 mm² | N/A |

| Base clock | 2000 MHz | 300 MHz |

| Boost clock | 2050 MHz | 1300 MHz |

| Memory | 6 GB GDDR6 | System Shared |

| Memory bus | 96 bit | System Shared |

| Memory bandwidth | 186.0 GB/s | System Dependent |

| Shading units | 1024 | 256 |

| TMUs | 64 | 16 |

| ROPs | 32 | 8 |

| RT cores | 8 | None |

| Pixel rate | 65.60 GPixel/s | 10.40 GPixel/s |

| Texture rate | 131.2 GTexel/s | 20.80 GTexel/s |

| FP32 | 4.198 TFLOPS | 665.6 GFLOPS |

| FP16 | 8.397 TFLOPS (2:1) | 1,331.2 GFLOPS (2:1) |

| TDP | 75 W | 15 W |

| Slot width | Dual-slot | IGP |

| Power connectors | 1x 8-pin | None |

| Suggested PSU | 250 W | None |

| Bus interface | PCIe 4.0 x8 | Ring Bus |

| Display outputs | 1x HDMI 2.1, 3x DisplayPort 2.0 | Motherboard Dependent |

| DirectX | 12 Ultimate (12_2) | 12 (12_1) |

| Release date | 2022-06-13 | 2021-03-29 |

| Launch MSRP | 149 USD | None |

Head-to-Head Benchmarks

Only two benchmark tests were run across both GPUs, and the Arc A380 wins both decisively.

In Geekbench OpenCL, the Arc A380 scores 38,224 versus the UHD Graphics 750's 6,743. That is a 466.9% lead. This is a compute-oriented test that exercises raw throughput, and the Arcade's massive advantage in shading units (1,024 vs 256), TMUs (64 vs 16), and memory bandwidth (186.0 GB/s vs system shared) shows up directly. This result is far beyond the differences seen in the average benchmark scores, confirming that the Arcade is not just a little faster, but a different class of device for compute workloads.

In Geekbench Vulkan, the Arc A380 scores 36,736 versus 8,138 for the UHD Graphics 750. The 351.4% margin is slightly smaller than the OpenCL gap, but still enormous. The Vulkan test benefits from the Arcade's PCIe 4.0 x8 interface and GDDR6 memory, which avoids the system memory bottleneck of the integrated GPU. The UHD 750's Ring Bus interface and shared memory architecture limit its ability to benefit from the same driver and API optimizations.

The recorded wins are 2 for the Arc A380 and 0 for the UHD Graphics 750. The database also lists several other benchmarks for the Arc A380, but the UHD Graphics 750 has no scores for those tests, so no comparison is possible. What is clear is that when both GPUs are run through the same two workloads, the discrete card outperforms the integrated solution by a margin that leaves no doubt about which one is faster.

Where Each One Wins

The Arc A380 wins in every scenario that involves actual GPU processing. It dominates compute via OpenCL, with a 466.9% advantage over the UHD Graphics 750. It dominates graphics via Vulkan, with a 351.4% advantage. Its 6 GB of GDDR6 memory, 186.0 GB/s bandwidth, and 8 ray tracing cores make it a viable choice for light gaming, content creation, and compute projects that can use the Xe-HPG feature set. Its DirectX 12 Ultimate support means it can run titles that require DX12_2 features, which the UHD Graphics 750 cannot claim.

The UHD Graphics 750 wins only in scenarios where the Arc A380 cannot be installed. It is an integrated GPU with a 15 W TDP, no power connector, and no expansion slot requirement. It is built into the Rocket Lake processor and uses the system's main memory, so it has zero added hardware cost. Its only wins are practical: it fits in a system with no PCIe slot, uses negligible power, and produces no heat beyond the CPU's own cooler. The database shows it at the 40th percentile of all GPUs, which is respectable for an IGP, but its absolute performance is low. Its nearest rival, the NVIDIA GeForce GTX 1650, is only 0.4% higher in average score, which suggests that the UHD 750 is not far off from some entry-level discrete cards in aggregate, but the head-to-head tests show that the Arc A380 is in a completely different league.

For a builder with a choice, the data says: if you need to render frames, compute, or use ray tracing, buy the Arc A380. If you need a no-power, no-slot display adapter that does not require an expansion card, the UHD Graphics 750 is the only one of the two that can fit in that role. There is no workload in the recorded benchmarks where the integrated GPU wins, so the decision rests entirely on system constraints.

DETAILED SPECIFICATIONS

SPECIFICATION
A380
UHD Graphics 750
Core Specs
Shading Units
1,024
256 -75.0%
Shaders
1,024
256 -75.0%
TMUs
64
16 -75.0%
ROPs
32
8 -75.0%
Execution Units
128
32 -75.0%
Clocks
Base Clock
2000 MHz
300 MHz
Boost Clock
2050 MHz
1300 MHz
Memory Clock
1937 MHz 15.5 Gbps effective
System Shared
Memory
Memory Size
6 GB
System Shared
VRAM (MB)
6,144
Memory Type
GDDR6
System Shared
Memory Bus
96 bit
System Shared
Bandwidth
186.0 GB/s
System Dependent
Cache
L2 Cache
4 MB
Performance
Pixel Rate
65.60 GPixel/s
10.40 GPixel/s
Texture Rate
131.2 GTexel/s
20.80 GTexel/s
FP32 (TFLOPS)
4.198 TFLOPS
665.6 GFLOPS
FP64 (TFLOPS)
1,049.6 GFLOPS (1:4)
FP16 (TFLOPS)
8.397 TFLOPS (2:1)
1,331.2 GFLOPS (2:1)
AI/RT
RT Cores
8
XMX Cores
128
Power
TDP
75 W
15 W
TDP (W)
75
15 -80.0%
Suggested PSU
250 W
Power Connectors
1x 8-pin
Architecture
Architecture
Xe-HPG
Generation 12.1
GPU Name
DG2-128
Rocket Lake
Generation
Alchemist (Arc 3)
HD Graphics (Rocket Lake)
Process Size
6 nm
14 nm+++
Transistors
7,200 million
Die Size
157 mm²
Foundry
TSMC
Intel
Density
45.9M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 (12_1)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
Shader Model
6.6
6.6
Physical
Slot Width
Dual-slot
IGP
Length
222 mm 8.7 inches
Height
114 mm 4.5 inches
Outputs
1x HDMI 2.13x DisplayPort 2.0
Motherboard Dependent
Bus Interface
PCIe 4.0 x8
Ring Bus
Other
Launch Price
149 USD
Production
End-of-life
End-of-life
Predecessor
Xe Graphics
Successor
Battlemage
View Arc A380 Details View UHD Graphics 750 Details